Title :
A Solution to Dimensionality Curse of BP Network in Pattern Recognition Based on RS Theory
Author :
Qin, Haiou ; Tang, Shixi
Author_Institution :
Dept. of Inf. Sci. & Technol., YanCheng Teachers Univ., Yancheng, China
Abstract :
In order to solve the dimensionality curse of BP neural network in pattern recognition, this paper proposes a model of dimensionality reduction which based on rough set theory. While training network, the model first carries out attribute reduction based on rough set theory, and then picks up important characteristics of ideal samples to reduce input space dimensions. Hence the speed of network training is increased. During pattern recognition process, the model picks up important characteristics of practical samples and denoise, so the recognition rate is increased. For illustration, a letter recognition example is used to test the feasibility of this model. The Results of experiment show that the model can effectively solve the dimensionality curse of BP network in pattern recognition.
Keywords :
backpropagation; data reduction; neural nets; pattern recognition; rough set theory; BP neural network training; attribute reduction; dimensionality curse; pattern recognition; rough set theory; space dimensionality reduction; Artificial neural networks; Feedforward systems; Information systems; Knowledge representation; Neural networks; Neurons; Pattern recognition; Rough sets; Set theory; Symmetric matrices; BP network; attribute reduction; curse of dimensionality; pattern recognition; rough sets;
Conference_Titel :
Computational Sciences and Optimization, 2009. CSO 2009. International Joint Conference on
Conference_Location :
Sanya, Hainan
Print_ISBN :
978-0-7695-3605-7
DOI :
10.1109/CSO.2009.324
